© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19794
    Prev
    Next
    INDEX
    Explanations

    whether followed by alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķ¦
    -0.11
    æĹ¶ä»£çļĦ
    -0.10
    é³Į
    -0.10
    æ¡ĮåŃIJä¸Ĭ
    -0.10
    槲
    -0.10
    绽
    -0.09
    èľľ
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    èĮĤ
    -0.09
    åĴ§
    -0.09
    POSITIVE LOGITS
    åĩºäºİ
    0.14
    æºIJèĩª
    0.10
    enance
    0.08
    ä¸į说
    0.08
    åIJĦæł·
    0.08
    åħ¥åı£
    0.08
    èĥ½åIJ¦
    0.08
    IDL
    0.08
    说
    0.08
    ä¸įåıĬ
    0.07
    Activations Density 0.018%

    No Known Activations